New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Coreweave Performance Tuning

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Optimize CoreWeave GPU inference latency and throughput. An agent skill from jeremylongshore/tons-of-skills-marketplace.

MITAuto-check passedAI & LLM Engineering

Install Coreweave Performance Tuning

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill coreweave-performance-tuning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace coreweave-performance-tuning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/coreweave-performance-tuning .claude/skills/coreweave-performance-tuning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
coreweave-performance-tuning
GitHub stars
2.8k
Token cost
~1.1k tokens
SKILL.md length
369 words
Files
1
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Optimize CoreWeave GPU inference latency and throughput. An agent skill from jeremylongshore/tons-of-skills-marketplace.

  • Works in 4 steps: Change one variable at a time—batching,… → Run the agreed load and quality… → Promote a canary only when all SLO and… → …
  • Reducing inference latency
  • SKILL.md covers Overview, Prerequisites, Instructions and GPU Selection by Workload, plus 8 more sections
  • Calls kubectl

What it does

Coreweave Performance Tuning is an agent skill from jeremylongshore/tons-of-skills-marketplace. Optimize CoreWeave GPU inference latency and throughput. Use when reducing inference latency, maximizing GPU utilization, or tuning batch sizes and concurrency. Trigger with phrases like "coreweave performance", "coreweave latency", "coreweave throughput", "optimize coreweave inference".

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Designed for Claude Code

It sits in AI & LLM Engineering, covering LLM inference and serving. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Reducing inference latency
  • Maximizing GPU utilization
  • Tuning batch sizes and concurrency
  • With phrases like coreweave performance

Example prompts

  • “coreweave performance”
  • “coreweave latency”
  • “coreweave throughput”
  • “/coreweave-performance-tuning”

Requirements

  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(kubectl:*)

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Change one variable at a time—batching, GPU class, replicas, or memory target.
  2. Run the agreed load and quality evaluation in staging, then compare with baseline.
  3. Promote a canary only when all SLO and quality thresholds pass for the observation window.
  4. Revert to the prior manifest when latency, errors, or quality crosses the agreed limit.

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash(kubectl:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • kubectl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • coreweave.com
    • docs.vllm.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Claude Code

    From compatibility in the SKILL.md frontmatter.

Context cost

Coreweave Performance Tuning loads about 1.1k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 369 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 369 words, ~1,129 tokens.

Download SKILL.mdSave it as .claude/skills/coreweave-performance-tuning/SKILL.md (or your agent's skills folder).
name
coreweave-performance-tuning
description
Optimize CoreWeave GPU inference latency and throughput. Use when reducing inference latency, maximizing GPU utilization, or tuning batch sizes and concurrency. Trigger with phrases like "coreweave performance", "coreweave latency", "coreweave throughput", "optimize coreweave inference".
allowed-tools
Read, Write, Edit, Bash(kubectl:*)
compatibility
Designed for Claude Code
version
1.11.0
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, gpu-cloud, kubernetes, inference, coreweave

CoreWeave Performance Tuning

Community-contributed. Not affiliated with, endorsed by, or sponsored by CoreWeave, Inc. CoreWeave is a registered trademark of CoreWeave, Inc.

Overview

Tune GPU inference or training only against measured throughput, latency, quality, availability, and cost targets. A higher utilization figure is not a success if it causes queueing, memory pressure, or a customer-facing SLO regression.

Prerequisites

  • A baseline for p95/p99 latency, throughput, error rate, GPU memory, and utilization.
  • A representative non-sensitive evaluation set and a named owner for the SLO.
  • A staging lane and a rollback manifest for every resource or serving change.

Instructions

  1. Change one variable at a time—batching, GPU class, replicas, or memory target.
  2. Run the agreed load and quality evaluation in staging, then compare with baseline.
  3. Promote a canary only when all SLO and quality thresholds pass for the observation window.
  4. Revert to the prior manifest when latency, errors, or quality crosses the agreed limit.

GPU Selection by Workload

WorkloadRecommended GPUWhy
LLM inference (7-13B)A100 80GBGood balance of memory and cost
LLM inference (70B+)8xH100NVLink for tensor parallelism
Image generationL40Good for diffusion models
Training (large models)8xH100 SXM5Fastest interconnect
Batch processingA100 40GBCost-effective

Inference Optimization

yaml
# Continuous batching with vLLM
containers:
  - name: vllm
    args:
      - "--model=meta-llama/Llama-3.1-8B-Instruct"
      - "--max-num-batched-tokens=8192"
      - "--max-num-seqs=256"
      - "--gpu-memory-utilization=0.90"
      - "--enable-prefix-caching"
      - "--dtype=float16"

Autoscaling Tuning

yaml
# HPA based on GPU utilization
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: inference-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: inference-server
  minReplicas: 2
  maxReplicas: 10
  metrics:
    - type: Pods
      pods:
        metric:
          name: DCGM_FI_DEV_GPU_UTIL
        target:
          type: AverageValue
          averageValue: "70"

Performance Benchmarks

MetricA100-80GBH100-80GB
Llama-8B tokens/sec~2,000~4,500
Llama-70B tokens/sec~200 (4x)~500 (4x)
Cold start (vLLM)30-60s20-40s
Show full SKILL.md (145 more words)Show less

Output

  • A measured performance baseline and a single reviewed tuning recommendation.
  • A canary result covering throughput, latency, error rate, GPU memory, and quality.
  • A versioned rollback manifest with a named decision owner.

Error Handling

ConditionSafe response
GPU memory exceeds the guardrailRestore the previous batch or memory setting and investigate the request distribution.
Latency rises after batchingReduce concurrency or restore replica count; do not raise timeouts to hide the regression.
Evaluation quality dropsRoute the canary back to the baseline configuration and preserve aggregate results.
Autoscaler oscillatesRestore stable bounds and tune from a longer measured window.

Examples

Run a staging canary and save only aggregate measurements for review:

bash
kubectl -n inference-staging apply -f inference-tuned.yaml
kubectl -n inference-staging rollout status deployment/inference-server --timeout=10m
./scripts/load-test --target staging --duration 15m --report aggregate.json

If the report breaches the signed SLO or quality threshold, apply the previous manifest immediately and attach aggregate.json to the change record.

Resources

Next Steps

For cost optimization, see coreweave-cost-tuning.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/coreweave-performance-tuning of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287

Compare with similar skills

Coreweave Performance Tuning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Coreweave Performance Tuning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Coreweave Performance Tuning this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1.1kAutomated safety check: PassMIT
SageMaker Serving Image Selectionhuggingface/skills11k1 repos~4.6kAutomated safety check: PassApache-2.0
Hugging Face Local Model Evalshuggingface/skills11k2 repos~1.6kAutomated safety check: PassApache-2.0
Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide1.7k—~1.7kAutomated safety check: PassMIT
CI Fails Buildkiteguqiong96/Lvllm4652 repos~349Automated safety check: PassApache-2.0
Subwave LLM Benchperminder-klair/subwave1.4k—~2.4kAutomated safety check: NotesMIT

Similar skills

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Local Model Evals

    huggingface/skills

    Official

    Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

    11k GitHub starsUsed in 2 repos~1.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Qwen Mtp Gguf

    R6410418/Jackrong-llm-finetuning-guide

    Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

    1.7k GitHub stars~1.7k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • CI Fails Buildkite

    guqiong96/Lvllm

    Fetch and diagnose vLLM Buildkite CI failure logs. An agent skill from guqiong96/Lvllm.

    465 GitHub starsUsed in 2 repos~349 tokens
    AI & LLM EngineeringAuto-check passed

  • Subwave LLM Bench

    perminder-klair/subwave

    Benchmark and compare LLM models for SUB/WAVE's on-air calls — track picks, segments, listener requests, DJ scripts, banter, and programme beats — in both candidate-pool and agent modes, using…

    1.4k GitHub stars~2.4k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Adapt New Diffusion Model

    intel/auto-round

    Official

    Adapt AutoRound to support a new diffusion model architecture (DiT, UNet, hybrid AR+DiT).

    1.6k GitHub stars~2.8k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo

  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes

  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed

  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Categories

Questions about Coreweave Performance Tuning

What does Coreweave Performance Tuning do?

Optimize CoreWeave GPU inference latency and throughput. An agent skill from jeremylongshore/tons-of-skills-marketplace. Coreweave Performance Tuning is an agent skill from jeremylongshore/tons-of-skills-marketplace. Optimize CoreWeave GPU inference latency and throughput.

When should I use Coreweave Performance Tuning?

Coreweave Performance Tuning fits situations like: reducing inference latency; maximizing GPU utilization; tuning batch sizes and concurrency; with phrases like coreweave performance.

How do I install Coreweave Performance Tuning in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill coreweave-performance-tuning -a claude-code`. Or copy the skill folder (skills/.curated/coreweave-performance-tuning in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/coreweave-performance-tuning in your project. Claude Code loads it when a task matches its description.

How do I install Coreweave Performance Tuning in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill coreweave-performance-tuning -a codex`. Or copy the skill folder (skills/.curated/coreweave-performance-tuning in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/coreweave-performance-tuning in your project. Codex loads it when a task matches its description.

Can I use Coreweave Performance Tuning in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill coreweave-performance-tuning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/coreweave-performance-tuning, .gemini/skills/coreweave-performance-tuning, .github/skills/coreweave-performance-tuning and .opencode/skills/coreweave-performance-tuning in your project.

What does Coreweave Performance Tuning need to run?

Going by SKILL.md and its folder, Coreweave Performance Tuning needs the command-line tools its instructions call (kubectl). Its frontmatter pre-approves these tools: Read, Write, Edit, Bash(kubectl:*). Compatibility (from SKILL.md): Designed for Claude Code.

Does Coreweave Performance Tuning access the network?

SKILL.md names 2 domains. As links in the text: coreweave.com and docs.vllm.ai. This is read from the text; nothing was executed.

Is Coreweave Performance Tuning safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Coreweave Performance Tuning use?

Coreweave Performance Tuning is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Coreweave Performance Tuning use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Coreweave Performance Tuning?

Skills that share tags, products or a category with Coreweave Performance Tuning: SageMaker Serving Image Selection (huggingface/skills, 11k stars), Hugging Face Local Model Evals (huggingface/skills, 11k stars), Qwen Mtp Gguf (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars) and CI Fails Buildkite (guqiong96/Lvllm, 465 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Coreweave Performance Tuning?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.